INDEX

Explanations

address

The neuron is triggered by mentions of “address” (and related location/address fields), i.e. when the text refers to a postal or street address.

New Auto-Interp

Configuration

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

Negative Logits

戋

-1.75

enment

-1.66

ivamente

-1.65

their

-1.61

ل

-1.59

StructEnd

-1.55

艄

-1.55

(!__

-1.54

</

-1.52

バ

-1.52

POSITIVE LOGITS

逦

1.73

Our

1.63

 nedenle

1.63

指向

1.56

 address

1.55

判斷

1.51

to

1.49

1.48

 demás

1.46

 where

1.45

Activations Density 0.010%